Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical programming concepts and operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.69
     Vaugh
    -0.68
    ONSORED
    -0.63
     undermin
    -0.57
     disadvant
    -0.56
    oulos
    -0.55
    terday
    -0.54
     Slater
    -0.54
     frontline
    -0.54
     millenn
    -0.53
    POSITIVE LOGITS
    ¶
    0.77
     Profile
    0.67
    optional
    0.67
     optionally
    0.66
     comma
    0.64
     verb
    0.63
     optional
    0.63
     integer
    0.63
     lookup
    0.62
     edit
    0.62
    Act Density 4.248%

    No Known Activations